Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 21626
    Prev
    Next
    INDEX
    Explanations

    words related to immigration or transformation

    oai_token-act-pair · gpt-3.5-turbo

    variations of the prefix "imm," indicating a focus on themes of immigration, immaturity, or immobility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ¶ħ
    -0.90
     lawy
    -0.76
    bys
    -0.75
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.74
    ģĸ
    -0.70
    rists
    -0.68
    BY
    -0.66
    \\\\\\\\
    -0.66
     Warfare
    -0.65
     strip
    -0.65
    POSITIVE LOGITS
    igrants
    1.46
    igrant
    1.39
    aterial
    1.34
    ersion
    1.29
    agine
    1.29
    igration
    1.29
    ovable
    1.28
    igrated
    1.24
    ortality
    1.21
    obil
    1.20
    Activations Density 0.031%

    No Known Activations